Browsing by Author "Silva, Eduardo Coelho da"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- Mineração Preditiva de Processos - Otimização de processos de negócio através de técnicas preditivasPublication . Silva, Eduardo Coelho da; Marreiros, Maria Goreti CarvalhoThe complexity of business processes has reached an all-time high and the environments in which organisations operate have never been so competitive and dynamic. This created the need for business processes to be continuously analysed, improved, and supported by an adequate set of tools and techniques, which led to the conception of Process Mining (PM). Predictive Process Mining (PPM) emerges as the integration of PM with predictive mecha nisms, with the goal of enabling more proactive decision-making and problem-solving, com pared to the reactive approach adopted with traditional PM. This dissertation aims to raise awareness of its benefits and increase its adoption, by studying real-world applications of PPM in a multinational organisation. During this work, interviews conducted with key business users led to the conclusion that PPM, from a management perspective, not only improves process transparency and under standing of its complexities, but also allows the future behaviour of ongoing processes to be predicted and actions taken to align them with business interests. Regarding operations, the interviewees expect the change to a more proactive approach to lead to an improvement in process efficiency, resource management, and performance metrics (e.g., user satisfaction, lead time), as a result of smoother process execution, with reduced delays and setbacks. To support these expectations and study the application of predictive techniques in PPM, two distinct solutions have been developed. The first use case: Next-Event Prediction, covers a specific sequence of steps from a purchasing process and aims to predict whether a purchase request will be rejected during the review stage, following its creation. The second use case: Outcome Prediction, covers a complex multi-step change approval process and aims to make an early prediction on whether the decision will be delayed or not, based on a predefined deadline. In both cases, an early prediction allows users to make the necessary changes to avoid an undesirable outcome. During development, process analyses revealed significant potential for the process perfor mance to be optimised and allowed the definition of Key Performance Indicators (KPIs) to measure the real impact of the use cases once they are deployed to production. When it comes to the implementation, several techniques have been studied, with particular empha sis on the analysis of different representations for the process data (e.g., aggregated vs. sequential), and the performance comparison between ensemble (e.g., eXtreme Gradient Boosting (XGBoost)) and deep learning models (e.g., Long Short Term Memory (LSTM)). In both use cases, XGBoost demonstrated notable performance and outperformed the other models, with F1-Scores ranging from 84% to 87%. In the end, not only have the initial expectations from stakeholders been met, but they have also gained a better understanding of their needs and PPM’s capabilities. By maintaining close communication with end users and stakeholders, addressing their needs and concerns, and building on top of the work from this thesis, PPM will surely be on the right track to realise its potential and thrive in the ever-evolving business landscape, helping organisations adapt to the challenges and opportunities that lie ahead.